Un modelo de pronóstico dinámico para la descarga promedio mensual de la estación de aforo, puente carretera Tumbes: enero de 1995 - Mayo de 2007 (m3/s)

• Autor: Blas Pérez, Juan Santiago
• Formato: tesis de maestría
• Fecha de Publicación: 2013
• Institución: Universidad Nacional de Trujillo
• Repositorio: UNITRU-Tesis
• Lenguaje: español
• OAI Identifier: oai:dspace.unitru.edu.pe:20.500.14414/12158
• Enlace del recurso: https://hdl.handle.net/20.500.14414/12158
• Nivel de acceso: acceso abierto
• Materia: Investigación; Metodología; Pronóstico

ABSTRACT The present work, research, descriptive, longitudinal, is based on the theory of the time series analysis with the methodology of Box and Jenkins was conducted for the purpose of analyzing the historical series of the monthly average Downloads (in m3/s) of the Station of Seating capacity: Tumbes Bridge Highway, For 149 consecutive months between January 1995 - May 2007, obtained from the Ministry of Agriculture - National Institute of Natural Resources of Tumbes with the aim of determining a forecasting model dynamic of these downloads, that would allow us to make predictions and assess the behavior for its control. The data from the first 149 months were used for the estimation of the model, and the remaining 6 months for the validation of the model. The program was carried out using EVIEWS, version 5. In the results was obtained that the series presented a study in non-stationary behavior in mean and variance, is applied the differentiation of the historical series, which generated moving-average in half, but not in variance, doing necessary use the sarima model. Finally it was felt this model SARIMA (0, 1, 1) (2, 0, 3), and with adequate validity of prognosis, which calculates the Average Monthly Downloads (in m3/s) of the Station of Seating capacity: Tumbes Bridge Highway, with a standard error of estimate of 62.27 m3/s average monthly, an explanation of the model on the average monthly Downloads, Gauging Station Tumbes, Bridge Highway: January 1995 - May 2007 of 78.37 %.